llm-streaming-integration

Community

Efficient LLM streaming with a unified gateway.

AuthorStevenWXY
Version1.0.0
Installs0

System Documentation

What problem does it solve?

This guide provides best practices for integrating and handling streaming LLM responses across multiple providers, including SSE, Electron IPC, and React UI rendering, with robust error handling and token budgeting.

Core Features & Use Cases

  • Multi-model streaming support: Claude, GPT, Gemini, and DeepSeek with a single gateway.
  • SSE handling, IPC-based streaming in Electron, and real-time UI updates in React.
  • Context assembly, adapter-based model integration, and robust retry with exponential backoff.
  • Secure, isolated AI calls in the main process, with BYOK-style key management and local key storage.

Quick Start

Configure the AI gateway, adapters, and IPC streaming in your Electron app to observe live AI responses.

Dependency Matrix

Required Modules

None required

Components

Standard package

💻 Claude Code Installation

Recommended: Let Claude install automatically. Simply copy and paste the text below to Claude Code.

Please help me install this Skill:
Name: llm-streaming-integration
Download link: https://github.com/StevenWXY/Project-Sibylla/archive/main.zip#llm-streaming-integration

Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
View Source Repository

Agent Skills Search Helper

Install a tiny helper to your Agent, search and equip skill from 471,000+ vetted skills library on demand.